Ticket to activate JuliaRegistrator for new versions

[behinger]

@JuliaRegistrator register

Unfold 0.4.0 Release notes

New feature: Fit multiple mass-univariate models at the same time. Similar to how you can fit multiple events/basisfunction in an UnfoldLinearModelContinuousTime, you can now do:
fit(UnfoldModel,Dict(:A=>(@formula(0~1+a+b),times),:B=>(@formula(0~1+c+b,times)),evts,data_epoched)

Note that the two times vectors have to be the same right now - this is more an internal issue than a major requirement.

Internal feature Missing values are now explicitly disallowed, fixing a bug with BSplineTerms. Thank you @jschepers for reporting

[JuliaRegistrator]

Registration pull request created: JuliaRegistries/General/80236

After the above pull request is merged, it is recommended that a tag is created on this repository for the registered package version.

This will be done automatically if the Julia TagBot GitHub Action is installed, or can be done manually through the github interface, or via:

git tag -a v0.4.0 -m "<description of version>" fff1f808f515decedc2287451150fb4aceed1611
git push origin v0.4.0

[behinger]

@JuliaRegistrator register

Bugfix release 0.4.1

• Fix a bug introduced in 0.4.0 where effects was not working correctly
• Fix a bug where missing values in the second event influence the first event (in case of splines)

[JuliaRegistrator]

Registration pull request created: JuliaRegistries/General/80262

After the above pull request is merged, it is recommended that a tag is created on this repository for the registered package version.

This will be done automatically if the Julia TagBot GitHub Action is installed, or can be done manually through the github interface, or via:

git tag -a v0.4.1 -m "<description of version>" d2f30ddb39db0745799a5b0c868015127d30a33b
git push origin v0.4.1

[behinger]

@JuliaRegistrator register

Release notes

Bugfix release

• remove debug statement for splines
• add zenodo entry
• fix documentation effects.jl

[JuliaRegistrator]

Error while trying to register: "Tag with name v0.4.1 already exists and points to a different commit"

[behinger]

@JuliaRegistrator register

Release notes

Bugfix release

remove debug statement for splines
add zenodo entry
fix documentation effects.jl

[JuliaRegistrator]

Registration pull request created: JuliaRegistries/General/83718

After the above pull request is merged, it is recommended that a tag is created on this repository for the registered package version.

This will be done automatically if the Julia TagBot GitHub Action is installed, or can be done manually through the github interface, or via:

git tag -a v0.4.2 -m "<description of version>" 7eaaa5530640cf12072f1ccc108ac0e4c4a15001
git push origin v0.4.2

[behinger]

@JuliaRegistrator register

Release notes:

New features:

• circular/periodic splines (circspl(colName,10,-π ,π)). Thanks to @lokmanfl for prior work on this (Update splinepredictors.jl #109)
• optimized save / load via JLD2. Internally the designmatrix is not saved, thus even large models have ~20mb (instead of 1-2Gb (like in Matlab). save(joinpath(save_path, "uf_model1.jld2"), m1) and load(joinpath(save_path, "uf_model1.jld2"), UnfoldModel, generate_Xs=false) does the trick (note: generate_Xs is true by default. But it typically is quite slow (up to 30s) - often the already fitted version is saved, thus the big Xs matrix are not needed. Thus generate_Xs=false is quite helpful! (Add io functions #114) thanks to @jschepers

Breaking changes

• splines have been rewritten. No more anonymous functions, move from BSplines.jl to BSplineKit, but most importantly spl(col,5) now results in one less spline than before (it results in a splineset of 5 spline-functions, before it resultet in 6 spline-functions, as one is removed due to the intercept)! We now follow the matlab-unfold toolbox. Thus minimal splines is now 4, not 3!

Other changes

• Added AbstractSplineTerm to facilitate further investigations into splines (and potential penalized splines)
• Better show() functions for timeexpandedTerms and DesignMat

[JuliaRegistrator]

Registration pull request created: JuliaRegistries/General/84462

After the above pull request is merged, it is recommended that a tag is created on this repository for the registered package version.

This will be done automatically if the Julia TagBot GitHub Action is installed, or can be done manually through the github interface, or via:

git tag -a v0.5.0 -m "<description of version>" 2fa897b0a0da83a3f3dfa208b35a54754286b43d
git push origin v0.5.0

[behinger]

@JuliaRegistrator register

Release notes:

New features:

• circular/periodic splines (circspl(colName,10,-π ,π)). Thanks to @lokmanfl for prior work on this (Update splinepredictors.jl #109)
• optimized save / load via JLD2. Internally the designmatrix is not saved, thus even large models have ~20mb (instead of 1-2Gb (like in Matlab). save(joinpath(save_path, "uf_model1.jld2"), m1) and load(joinpath(save_path, "uf_model1.jld2"), UnfoldModel, generate_Xs=false) does the trick (note: generate_Xs is true by default. But it typically is quite slow (up to 30s) - often the already fitted version is saved, thus the big Xs matrix are not needed. Thus generate_Xs=false is quite helpful! (Add io functions #114) thanks to @jschepers

Breaking changes

• splines have been rewritten. No more anonymous functions, move from BSplines.jl to BSplineKit, but most importantly spl(col,5) now results in one less spline than before (it results in a splineset of 5 spline-functions, before it resultet in 6 spline-functions, as one is removed due to the intercept)! We now follow the matlab-unfold toolbox. Thus minimal splines is now 4, not 3!

Other changes

• Added AbstractSplineTerm to facilitate further investigations into splines (and potential penalized splines)
• Better show() functions for timeexpandedTerms and DesignMat

[JuliaRegistrator]

Registration pull request updated: JuliaRegistries/General/84462

After the above pull request is merged, it is recommended that a tag is created on this repository for the registered package version.

This will be done automatically if the Julia TagBot GitHub Action is installed, or can be done manually through the github interface, or via:

git tag -a v0.5.0 -m "<description of version>" e7592e081de2a0226624b6fad7ae4f61630e54b1
git push origin v0.5.0

[behinger]

@JuliaRegistrator register

Release notes:
Bugfix release.

• fix issues in documentation (update to new major UnfoldMakie version, upgrades some examples to use UnfoldSim)
• fix issue with missings in Effects.jl (occuring in out-of-domain prediction with splines)

[JuliaRegistrator]

Registration pull request created: JuliaRegistries/General/85719

After the above pull request is merged, it is recommended that a tag is created on this repository for the registered package version.

This will be done automatically if the Julia TagBot GitHub Action is installed, or can be done manually through the github interface, or via:

git tag -a v0.5.1 -m "<description of version>" c46a3aa00db188af1f0f1ff6a282c50ff23a117d
git push origin v0.5.1

[behinger]

@JuliaRegistrator register

[JuliaRegistrator]

Registration pull request created: JuliaRegistries/General/89177

After the above pull request is merged, it is recommended that a tag is created on this repository for the registered package version.

This will be done automatically if the Julia TagBot GitHub Action is installed, or can be done manually through the github interface, or via:

git tag -a v0.6.0 -m "<description of version>" eb406bda70e597d0ef98bb4024b07cc8c2cc84f8
git push origin v0.6.0

[JuliaRegistrator]

Registration pull request updated: JuliaRegistries/General/89177

After the above pull request is merged, it is recommended that a tag is created on this repository for the registered package version.

This will be done automatically if the Julia TagBot GitHub Action is installed, or can be done manually through the github interface, or via:

git tag -a v0.6.0 -m "<description of version>" c02a64a603ad0e730a449a003a7996243ec39cdf
git push origin v0.6.0

[behinger]

Release notes:
Breaking

• Introducing PackageExtensions Weak Dependencies #119:
  • In order to use MixedModels you have to manually load using MixedModels
  • In order to use spl(ABC,5) splines, you have to manually load using BSplineKit
  • In order to use solver_robust you have to manually load using RobustModels
    This features reduced the package loading time from 15-25s to just 2s on my computer 🚀.

New Features

• massive ⚡ speed-ups⚡ using the following "tricks":
  • New extension: GPU support (via using Krylov and solver_krylov(...;gpu=true), currently only CUDA support, but this is not a fundamental limitation, merely an implementation wise, 75s => 3s speedup! together with @jschepers
  • Multithreading (which is the new default), speedup 2-10x
  • Up to 80% smaller designmatrices (and thus faster fits), by removing unnecessary zeros via dropzeros - speedup untested
• ProgressBar in all solvers (can be deactivated)

Bugfixes

• fix bug with LMM random effects wrongly reordered LMMs: coeftable re-order bug #115,Random effects are reordered #33
• 2D data reshaping not working correctly bug: LMM mass univariate with 2-dim data #110, Massunivariate LMM with two dimensions results in "coef" error #83
• replaced some unnecessary dependencies (e.g. DSP)

[behinger]

@JuliaRegistrator register
Release notes:

• generate compat with breaking StatsModels v0.7 (@behinger)
• much improved speed of designmatrix generation in case of special circumstances of same event-kernel length for all events (the typical case) (@behinger)
• minor bugfixes

[JuliaRegistrator]

Registration pull request created: JuliaRegistries/General/92260

After the above pull request is merged, it is recommended that a tag is created on this repository for the registered package version.

This will be done automatically if the Julia TagBot GitHub Action is installed, or can be done manually through the github interface, or via:

git tag -a v0.6.1 -m "<description of version>" 9d01de09455f249e042e508efafda5a991a384b9
git push origin v0.6.1

[behinger]

@JuliaRegistrator register
Release notes:
- added rePCA for LMMs
- some minor bugfixes
- greatly improved type-stability, especially for time_expand
- potentially breaking: starting to deprecate FIRbasis.kernel field. kernel(firbasis) does not return the kernelfunction anylonger, which was required to be an anonymous function. Rather, it is replaced by kernel(firbasis,e) to directly calculate the kernel at e. While the FIRBasis Type changed, we have a @deprecate in place that should catch the old access.

[JuliaRegistrator]

Registration pull request created: JuliaRegistries/General/94021

After the above pull request is merged, it is recommended that a tag is created on this repository for the registered package version.

This will be done automatically if the Julia TagBot GitHub Action is installed, or can be done manually through the github interface, or via:

git tag -a v0.6.2 -m "<description of version>" 4ce920a22b8756208cf1b634921693a2e3b85266
git push origin v0.6.2

[JuliaRegistrator]

Registration pull request created: JuliaRegistries/General/109647

Tagging

After the above pull request is merged, it is recommended that a tag is created on this repository for the registered package version.

This will be done automatically if the Julia TagBot GitHub Action is installed, or can be done manually through the github interface, or via:

git tag -a v0.7.4 -m "<description of version>" 38adf5471b8164e0f5ffbf9330f0089f82ed946d
git push origin v0.7.4

[behinger]

@JuliaRegistrator register
Release Notes:

• improve tutorials
• a first fix for Term.jl output in Pluto.jl - current bug: no output via Documenter.jl

[JuliaRegistrator]

Registration pull request created: JuliaRegistries/General/110816

Tagging

After the above pull request is merged, it is recommended that a tag is created on this repository for the registered package version.

This will be done automatically if the Julia TagBot GitHub Action is installed, or can be done manually through the github interface, or via:

git tag -a v0.7.5 -m "<description of version>" 41ad19e776b2f3d44c532b50b5fd4fa04eb1bfd7
git push origin v0.7.5

[behinger]

@JuliaRegistrator register
Release notes:

• bugfix for predict @ReneSkukies
• small documentation fixes
• fix Zenodo release metadata

[JuliaRegistrator]

Error while trying to register: Version 0.7.5 already exists

[behinger]

@JuliaRegistrator register
Release notes:

• bugfix for predict @ReneSkukies
• small documentation fixes
• fix Zenodo release metadata

[JuliaRegistrator]

Registration pull request created: JuliaRegistries/General/115556

Tagging

After the above pull request is merged, it is recommended that a tag is created on this repository for the registered package version.

This will be done automatically if the Julia TagBot GitHub Action is installed, or can be done manually through the github interface, or via:

git tag -a v0.7.6 -m "<description of version>" 47f86ea855a18e0a6971dc0f32e2cb2c850cda2d
git push origin v0.7.6

[behinger]

Release-notes 0.7.7

• rename 0.7.7-dev to 0.7.7 prior to register
• check docstring of "fit" and the solver-tutorial for up-to-dateness
• new structured backbone for the solver. Added ~6-7 new solvers. Split up the solver into prepare & solve functions that can be chained / modified easily. Added a reference document for exactly this.
• major bug: likelihoodratiotest was calculating wrong results (it was calculating a wrong likelihood). This lead to a breaking change in API, where now the data need to be provided as well.
• Bumped JLD to 0.5 - this means one cannot save files now and load it in older Unfold versions, but old unfold version files can still be loaded
• several small docstring fixes
• new CUDAextension, allowing to provide CuArray to automatically choose a better solver (still needs to be tested more though)
• fit now has an argument that can be set fit=false to not actually run the ´fit!` function, to do it later
• benchmarks now available comparing ~7 solver types with and without GPU, some with and without Float32. Improvements of up to 10x of the SOA-GPU solver were achieved

[behinger]

@JuliaRegistrator register
Release notes:

• new structured backbone for the solver. Added ~6-7 new solvers. Split up the solver into prepare & solve functions that can be chained / modified easily. Added a reference document for exactly this.
• major bug: likelihoodratiotest was calculating wrong results (it was calculating a wrong likelihood). This lead to a breaking change in API, where now the data need to be provided as well.
• Bumped JLD to 0.5 - this means one cannot save files now and load it in older Unfold versions, but old unfold version files can still be loaded
• several small docstring fixes
• new CUDAextension, allowing to provide CuArray to automatically choose a better solver (still needs to be tested more though)
• fit now has an argument that can be set fit=false to not actually run the ´fit!` function, to do it later
• benchmarks now available comparing ~7 solver types with and without GPU, some with and without Float32. Improvements of up to 10x of the SOA-GPU solver were achieved - fit a large model with 128 channels in wopping 8 seconds! Further tests are needed though to describe the accuracy drop that is achieved by solving X'Xb = X'y instead of Xb = y directly.

[JuliaRegistrator]

Registration pull request created: JuliaRegistries/General/119003

Tagging

After the above pull request is merged, it is recommended that a tag is created on this repository for the registered package version.

This will be done automatically if the Julia TagBot GitHub Action is installed, or can be done manually through the github interface, or via:

git tag -a v0.7.7 -m "<description of version>" a76a9727f4e17b2b91c20bd56cac3a8f610e2473
git push origin v0.7.7

[behinger]

@JuliaRegistrator register
Release Notes:

Feature:

• Scaled FIR basisfunction ala Cameron Hassall et al. 2022 implemented
• Scaled FIR basisfunction ala Blockdesign [0 0 0 1 1 1 1 1 0 0] implemented
• New tutorial for those

Backend

• Moved all actions to BestieTemplates.jl, including online Formatter action to pre-commit

[JuliaRegistrator]

Registration pull request created: JuliaRegistries/General/121650

Tagging

After the above pull request is merged, it is recommended that a tag is created on this repository for the registered package version.

This will be done automatically if the Julia TagBot GitHub Action is installed, or can be done manually through the github interface, or via:

git tag -a v0.7.8 -m "<description of version>" bb1a90b0afcce9774aafe03143fb6353d9b528cc
git push origin v0.7.8

[behinger]

@JuliaRegistrator register
Release Notes:

• Relaxed some compatability versions

[JuliaRegistrator]

Error while trying to register: Version 0.7.8 already exists

[behinger]

@JuliaRegistrator register
Release Notes:

Relaxed some compatability versions

[JuliaRegistrator]

Registration pull request created: JuliaRegistries/General/121725

Tagging

After the above pull request is merged, it is recommended that a tag is created on this repository for the registered package version.

This will be done automatically if the Julia TagBot GitHub Action is installed, or can be done manually through the github interface, or via:

git tag -a v0.7.9 -m "<description of version>" 267c1c955f084fe5e6fa6f3afa23fdbaff942a4f
git push origin v0.7.9

[behinger]

@JuliaRegistrator register
Release Notes:
breaking: Instead of having MixedModels as a PackageExtension, we will soon have the UnfoldMixedModels.jl package (after 3 days of registry period). This is necessary to export the UnfoldLinearMixedModels type, which is not exprtable from a PackageExtension. This split further allows for better code modularity.

That is, users now have to do: using UnfoldMixedModels rather than using Unfold, MixedModels

[JuliaRegistrator]

Registration pull request created: JuliaRegistries/General/122948

Tagging

After the above pull request is merged, it is recommended that a tag is created on this repository for the registered package version.

This will be done automatically if the Julia TagBot GitHub Action is installed, or can be done manually through the github interface, or via:

git tag -a v0.8.0 -m "<description of version>" 778c2db96e12ddc32213ea0b8b6aa9b5894370bd
git push origin v0.8.0

[behinger]

@JuliaRegistrator register
Release Notes:
Bugfix: residuals were incorrectly calculated in the case the data is longer than the model

[JuliaRegistrator]

Registration pull request created: JuliaRegistries/General/123047

Tagging

After the above pull request is merged, it is recommended that a tag is created on this repository for the registered package version.

This will be done automatically if the Julia TagBot GitHub Action is installed, or can be done manually through the github interface, or via:

git tag -a v0.8.1 -m "<description of version>" 7541c2b2b35980994ca4ee45f5baa8f20fa5e5fc
git push origin v0.8.1